Dynamic Hash Table Resource Allocation for Network Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computer networks face inefficiencies in dynamically allocating physical hash table resources to meet varying storage demands of lookup functions, such as bridging, routing, and Quality of Service, which affects network device performance and flexibility.
Innovation Solution
Implementing a system that dynamically allocates physical hash table resources by using logical hash tables and logical-physical resource mappings, allowing for flexible allocation and deallocation of resources based on demand, enabling efficient use of available resources across various network configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If physical hash table resources are statically allocated to lookup functions, then device complexity is reduced and ease of operation is improved, but adaptability to varying storage demands deteriorates
Solution Approach 1:
The patent segments physical hash table resources into multiple logical hash tables, each independently allocable to different lookup functions. This segmentation enables fine-grained control over resource allocation, allowing the system to adapt to varying storage demands of different lookup functions while maintaining manageable complexity through modular organization.
Solution Approach 2:
The patent implements dynamic allocation mechanisms where physical hash table resources can be flexibly assigned and reassigned to different logical hash tables based on runtime demands. The system continuously monitors storage requirements and adjusts allocations dynamically, transforming a static resource management approach into an adaptive one that responds to changing network conditions.
2Adaptability or versatility
If physical hash table resources are dynamically allocated to meet varying storage demands, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent introduces logical hash tables as an intermediary layer between physical hash table resources and lookup functions. This intermediary abstraction simplifies allocation management by providing a standardized interface that decouples the complexity of physical resource management from the needs of individual lookup functions, enabling flexible allocation without proportionally increasing overall system complexity.
Solution Approach 2:
The patent creates a universal resource allocation framework where a pool of physical hash table resources can serve multiple different lookup functions through logical hash tables. This multi-functional approach allows the same physical resources to be dynamically shared among routing, bridging, QoS, and other lookup functions, achieving high flexibility without requiring dedicated resources for each function.
3Reliability
If more physical hash table resources are allocated to accommodate peak demands, then reliability is improved, but loss of substance increases due to unused resources during low demand
Solution Approach 1:
The patent dynamically changes the allocation parameters of hash table resources based on actual demand conditions. During peak loads, more physical resources are allocated to ensure service reliability, while during low-demand periods, resources are deallocated or reassigned. This parameter adjustment mechanism ensures that the system maintains sufficient capacity for reliability while minimizing resource waste through continuous optimization of allocation levels.
Solution Approach 2:
The patent implements a resource recovery mechanism where excess hash table resources that are not currently needed by any lookup function are effectively discarded from active allocation and returned to the free pool. These recovered resources can then be reallocated when demand increases, ensuring that the system maintains reliability during peak loads without permanently allocating more resources than necessary, thereby avoiding continuous waste.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Examples relate to dynamic allocation of hash table resources. In one example, a computing device may: receive, from a particular lookup function of a plurality of lookup functions, a lookup request; identify, based on the particular lookup function, a logical hash table that corresponds to the particular lookup function, the logical hash table mapping to at least one physical hash table resource; obtain, from one of the at least one physical hash table resource, response data that is responsive to the lookup request; and provide the response data to the particular lookup function.